Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / mbzuai-oryx/Video-ChatGPT issues and pull requests

#125 - select frames

Issue - State: open - Opened by Arbor334 23 days ago - 1 comment

#124 - Is the linear layer initialized by llava's linear layer?

Issue - State: open - Opened by vhzy about 1 month ago

#123 - Cannot understand choice of mm_hidden_size 1024

Issue - State: open - Opened by jzyee about 1 month ago

#122 - xxx

Issue - State: closed - Opened by xuzq23 about 1 month ago

#121 - How to get the 100k original videos?

Issue - State: open - Opened by gaotiexinqu about 1 month ago - 2 comments

#120 - why i use A100 80G to inference so slow?

Issue - State: closed - Opened by Arbor334 about 2 months ago

#119 - Inquiry about Costs Associated with Video LLM Benchmarks

Issue - State: open - Opened by hb-jw about 2 months ago

#117 - Inference Code and Possible Utilization of Prompts

Issue - State: open - Opened by lucasxu777 2 months ago - 1 comment

#115 - evaluate_activitynet_qa

Issue - State: open - Opened by rixejzvdl649 3 months ago - 5 comments

#105 - Question about the semi-automatic dataset creation process

Issue - State: closed - Opened by ooza 4 months ago - 1 comment

#100 - Fix video_demo command in docs

Pull Request - State: closed - Opened by biphobe 5 months ago

#99 - How many frames are sampled per video for the training and testing process?

Issue - State: closed - Opened by Nastu-Ho 5 months ago - 5 comments

#98 - Download videos

Issue - State: closed - Opened by ZenMoore 5 months ago - 1 comment

#97 - How to download the ready LLaVA-Lightening-7B weights

Issue - State: open - Opened by SIGMIND 5 months ago - 5 comments

#96 - Why TGIF videos missed and can't be processed

Issue - State: closed - Opened by FlorientHuang 6 months ago - 3 comments

#95 - The responses from the offline_demo are garbled

Issue - State: closed - Opened by hlh2023214 6 months ago - 2 comments
Labels: demo

#94 - Question about consistency evaluation

Issue - State: closed - Opened by Eniac-Xie 6 months ago - 3 comments

#92 - I encountered an error while using "Run the Demo".

Issue - State: closed - Opened by ds-gong 6 months ago - 3 comments

#90 - 13B, 70B models

Issue - State: closed - Opened by MaxGonzalezSaez-Diez 7 months ago - 1 comment

#89 - GPT Judge does not work for the Prompt

Issue - State: closed - Opened by Jeff-Zilence 7 months ago

#88 - What is the formal name of the benchmark?

Issue - State: closed - Opened by zhimin-z 7 months ago - 3 comments

#86 - Code for Dataset Generation

Issue - State: open - Opened by yeliudev 8 months ago - 2 comments

#85 - Fail to execute Video-ChatGPT offline demo (when click "Upload Video")

Issue - State: closed - Opened by jeonggwanlee 8 months ago - 7 comments

#84 - About zero-shot test on TGIF-QA

Issue - State: closed - Opened by msra-jqxu 8 months ago - 1 comment

#83 - Why is OpenAI used for Activitynet-QA Evaluation?

Issue - State: closed - Opened by mcouts01 8 months ago - 3 comments

#81 - Can I deal with Chinese video?

Issue - State: closed - Opened by zhangyuereal 8 months ago - 1 comment

#80 - Llava Weights not available for running demo offline

Issue - State: closed - Opened by chakrabortyrajatsubhra 8 months ago - 2 comments

#78 - Fail to run Video-ChatGPT Demo Offline

Issue - State: closed - Opened by ChosenOne23 8 months ago - 2 comments
Labels: documentation, demo

#77 - Is Zeroshot evaluation on validation or test datasets

Issue - State: closed - Opened by KerolosAtef 9 months ago - 1 comment

#76 - The download of dataset

Issue - State: closed - Opened by liziming5353 9 months ago - 1 comment

#74 - Issue running offline demo

Issue - State: closed - Opened by Willyang1379 10 months ago - 1 comment

#73 - ActivityNet few shot videos can't be downloaded

Issue - State: closed - Opened by KerolosAtef 10 months ago - 7 comments

#72 - Inho jake park inho jake park where are you?

Issue - State: closed - Opened by CallmeBOKE 10 months ago

#71 - Question of training utilizing A6000

Issue - State: closed - Opened by xogud3373 10 months ago - 6 comments

#70 - Zhanwen/vtom 51 add multitask learning for frame idx gts

Pull Request - State: closed - Opened by zhanwenchen 10 months ago

#69 - Question about VideoInstruct_Dataset.json

Issue - State: closed - Opened by DarkLighter97 10 months ago - 1 comment

#68 - MSVD-QA and MSRVTT-QA evaluation

Issue - State: closed - Opened by KerolosAtef 11 months ago - 1 comment

#67 - Where can we download the video for VideoInstruct-100K?

Issue - State: closed - Opened by oximi123 11 months ago - 1 comment

#66 - Where to download the video in TGIF-QA

Issue - State: closed - Opened by LinB203 11 months ago - 4 comments

#65 - Where to download the video in MSRVTT-QA & How to evaluate TGIF-QA

Issue - State: closed - Opened by wcy1122 11 months ago - 6 comments

#64 - Error when running the demo.

Issue - State: closed - Opened by oximi123 11 months ago

#63 - Offline models and dataset download

Issue - State: closed - Opened by KerolosAtef 11 months ago - 5 comments

#62 - CUDA error: invalid device ordinal

Issue - State: closed - Opened by tkarthikeyan132 11 months ago - 3 comments

#60 - On the code of generating “pred_dir”

Issue - State: closed - Opened by wyzjack 11 months ago - 2 comments

#59 - Adding single video inference code without gradio web app.

Pull Request - State: closed - Opened by ashmalvayani 11 months ago - 2 comments

#58 - Video frame timestamp

Issue - State: closed - Opened by nahidalam 11 months ago - 1 comment

#57 - Model inference without Gradio

Issue - State: closed - Opened by tacit0428 11 months ago - 1 comment

#56 - online demo doesn't work now

Issue - State: closed - Opened by nigelnew 12 months ago - 1 comment

#55 - What is the minimum system requirement for training

Issue - State: closed - Opened by nahidalam about 1 year ago - 2 comments

#54 - How to evaluate the MSVD-QA and MSRVTT-QA

Issue - State: open - Opened by jhj7905 about 1 year ago - 3 comments

#53 - model inference

Issue - State: closed - Opened by Xiuyuan-Chen about 1 year ago - 2 comments

#52 - What is the size of the model compared in the experiment?

Issue - State: closed - Opened by jpthu17 about 1 year ago - 2 comments

#51 - can I train in one A100 80G GPU?

Issue - State: closed - Opened by hkuit about 1 year ago - 3 comments

#50 - Fail to run Video-ChatGPT Demo Offline

Issue - State: closed - Opened by JuanJia about 1 year ago - 2 comments

#49 - Loss curve during training

Issue - State: closed - Opened by FanScy about 1 year ago - 2 comments

#48 - Question about result

Issue - State: closed - Opened by jhj7905 about 1 year ago - 1 comment

#46 - Llama 2 7B

Issue - State: closed - Opened by roninio about 1 year ago - 1 comment

#45 - online demo fail

Issue - State: closed - Opened by Xiuyuan-Chen about 1 year ago - 1 comment

#44 - Error while deploying video-chatgpt locally

Issue - State: closed - Opened by EdenGabriel about 1 year ago - 1 comment

#43 - openai/clip-vit-large-patch14 were not used when initializing CLIPVisionModel

Issue - State: closed - Opened by minuenergy about 1 year ago - 3 comments

#42 - Few-shot video classification

Issue - State: closed - Opened by sevakon about 1 year ago - 1 comment

#41 - Missing config.json for Video-ChatGPT-7B when deployed on AWS Sagemaker

Issue - State: closed - Opened by alinaSarwar about 1 year ago - 1 comment

#40 - pydantic version problem

Issue - State: closed - Opened by Creator404 about 1 year ago - 1 comment

#39 - Website not working properly

Issue - State: closed - Opened by Muhammad-Soomro about 1 year ago - 3 comments

#38 - Website Down

Issue - State: closed - Opened by Muhammad-Soomro about 1 year ago - 2 comments

#37 - CLIPVisionModel and configuration warnings

Issue - State: closed - Opened by mario-holubar about 1 year ago - 1 comment

#36 - Can I apply your weights to vicuna 13b or 33b?

Issue - State: closed - Opened by msarkeshi about 1 year ago - 3 comments

#35 - Demo is dead :cry:

Issue - State: closed - Opened by karrymao about 1 year ago - 1 comment

#34 - the version of transformers

Issue - State: closed - Opened by zhl98 about 1 year ago - 1 comment

#33 - error while deploying video-chatgpt locally

Issue - State: closed - Opened by Xinxinatg about 1 year ago - 6 comments

#32 - Training GPU Device minimum Require Specs.

Issue - State: closed - Opened by BigJoon about 1 year ago - 4 comments

#31 - linear layer

Issue - State: closed - Opened by Adeelyousaf about 1 year ago - 1 comment
Labels: question

#30 - About Video Instruction Data Generation

Issue - State: closed - Opened by jhj7905 about 1 year ago - 1 comment
Labels: dataset

#29 - About the evaluation time

Issue - State: closed - Opened by wyzjack about 1 year ago - 2 comments
Labels: evaluation

#28 - Zero-Shot Question-Answer Evaluation of Accuracy

Issue - State: closed - Opened by msra-jqxu about 1 year ago - 11 comments
Labels: evaluation

#27 - hardware requirement for deploying video-chatgpt locally

Issue - State: closed - Opened by Xinxinatg about 1 year ago - 3 comments
Labels: question

#26 - ValueError: Some specified arguments are not used by the HfArgumentParser: ['--local-rank=1']

Issue - State: closed - Opened by BinZhu-ece about 1 year ago - 4 comments
Labels: environment

#25 - Setup Error during training

Issue - State: closed - Opened by BinZhu-ece about 1 year ago

#24 - Some video features are not found in pre-computed spatiotemporal CLIP features

Issue - State: closed - Opened by msra-jqxu about 1 year ago - 5 comments
Labels: documentation, training

#23 - Question about running video-chatgpt demo offline

Issue - State: closed - Opened by jhj7905 about 1 year ago - 13 comments
Labels: demo

#22 - Cannot load './LLaVA-Lightening-7B-v1-1'

Issue - State: closed - Opened by msra-jqxu about 1 year ago - 2 comments

#21 - training process: mat1 and mat2 must have the same dtype

Issue - State: closed - Opened by wang9danzuishuai about 1 year ago - 2 comments

#20 - Alternative choices for linear layer

Issue - State: closed - Opened by Kratos-Wen about 1 year ago - 2 comments

#19 - TypeError: forward () got an unexpected keyword argument "position_ids"

Issue - State: closed - Opened by GZHU-DVL about 1 year ago - 6 comments

#18 - During the demo, sometimes an exception occurs

Issue - State: closed - Opened by willzli about 1 year ago - 2 comments

#16 - Great work!

Issue - State: closed - Opened by wyzjack about 1 year ago - 6 comments

#14 - Longer frames issues.

Issue - State: closed - Opened by wang9danzuishuai about 1 year ago - 5 comments

#12 - from video_chatgpt.model.video_chatgpt import VideoChatGPTLlamaForCausalLM

Issue - State: closed - Opened by ChethanN01 over 1 year ago - 3 comments

#11 - video length

Issue - State: closed - Opened by ChethanN01 over 1 year ago - 1 comment